#8602 No human voice detected. Please confirm that human speech is present in the original file. [info.duration_after_vad=0.0s

117.182**4 Posted at: 2 hours ago

No human voice detected. Please confirm that human speech is present in the original file. [info.duration_after_vad=0.0s].
_kw={'beam_size': 5, 'best_of': 5, 'condition_on_previous_text': False, 'threshold': 0.2, 'no_speech_threshold': 0.6, 'temperature': 0.0, 'repetition_penalty': 1.0, 'compression_ratio_threshold': 2.4, 'initial_prompt': ''}
info=TranscriptionInfo(language='ja', language_probability=1, duration=89.838, duration_after_vad=0.0, all_language_probs=None, transcription_options=TranscriptionOptions(beam_size=5, best_of=5, patience=1, length_penalty=1, repetition_penalty=1.0, no_repeat_ngram_size=0, log_prob_threshold=-1.0, no_speech_threshold=0.6, compression_ratio_threshold=2.4, condition_on_previous_text=False, prompt_reset_on_temperature=0.5, temperatures=[0.0], initial_prompt=None, prefix=None, suppress_blank=True, suppress_tokens=(1, 2, 7, 8, 9, 10, 14, 25, 26, 27, 28, 29, 31, 58, 59, 60, 61, 62, 63, 90, 91, 92, 93, 359, 503, 522, 542, 873, 893, 902, 918, 922, 931,
......
ratio_threshold=2.4, condition_on_previous_text=False, prompt_reset_on_temperature=0.5, temperatures=[0.0], initial_prompt=None, prefix=None, suppress_blank=True, suppress_tokens=(1, 2, 7, 8, 9, 10, 14, 25, 26, 27, 28, 29, 31, 58, 59, 60, 61, 62, 63, 90, 91, 92, 93, 359, 503, 522, 542, 873, 893, 902, 918, 922, 931, 1350, 1853, 1982, 2460, 2627, 3246, 3253, 3268, 3536, 3846, 3961, 4183, 4667, 6585, 6647, 7273, 9061, 9383, 10428, 10929, 11938, 12033, 12331, 12562, 13793, 14157, 14635, 15265, 15618, 16553, 16604, 18362, 18956, 20075, 21675, 22520, 26130, 26161, 26435, 28279, 29464, 31650, 32302, 32470, 36865, 42863, 47425, 49870, 50254, 50258, 50359, 50360, 50361, 50362, 50363), without_timestamps=False, max_initial_timestamp=1.0, word_timestamps=True, prepend_punctuations='"\'“¿([{-', append_punctuations='"\'.。,,!!??::”)]}、', multilingual=False, max_new_tokens=None, clip_timestamps=[0.0], hallucination_silence_threshold=None, hotwords=''), vad_options=VadOptions(threshold=0.2, neg_threshold=None, min_speech_duration_ms=0, max_speech_duration_s=inf, min_silence_duration_ms=2000, speech_pad_ms=400))

trk=[TransCreate]: uuid='3483c5c2d1', proxy_str=None, cfg=[TaskCfgVTT]当前工作模式: 翻译视频 单视频模式
原始输入文件名: D:/Download/video_261031_213328.mp4,
输出结果保存到文件夹: D:/Download/_video_out/video_261031_213328-mp4,
临时文件夹: D:/win-pyvideotrans-v4.16/tmp/12564/3483c5c2d1
已选 清理已存在
已启用CUDA加速
语音识别:faster-whisper(内置), large-v3, 发音语言: 日语, LLM纠错, 数据类型:default
翻译渠道:Google(免费),原始语言:日语,目标语言:简体中文, 已选 发送完整字幕, settings.get('trans_thread')=10, settings.get('aitrans_thread')=40
未选 配音角色,不进行配音
字幕: 嵌入软字幕(双) 目标语言在上双字幕, precent=4, hasend=False, should_recogn=True, should_trans=True, should_dubbing=False, should_hebing=True, is_copy_video=False, video_codec_num=264, ignore_align=False, is_audio_trans=False, clone_ref='', should_recogn2=False, do_diarize=True
video_duration_ms=89874


=
system:Windows-10-10.0.26300-SP0
version:v4.17
frozen:True
language:zh_CN
root_dir:D:/win-pyvideotrans-v4.16

1 Replies

#1 DeepSeek reply at 2 hours ago

核心原因:VAD(语音活动检测)将整段音频判定为静音,duration_after_vad=0.0s 表示没有切出任何有效人声片段送入识别模型,因此直接报“未检测到人类语音”。当前阈值 threshold=0.2 已属较低值,说明要么原始音频确实缺少清晰人声,要么人声被环境噪声/低音量掩盖。

排查与解决步骤:

  1. 先用本地播放器确认该视频中确实存在清晰的说话声(如仅有音乐、环境音或人声极低,软件无法翻译),同时确认视频存在音轨。
  2. 若确认有人声但仍报此错,进入 菜单 → 工具/选项 → 高级选项 → 语音识别参数:

    • 将语音阈值进一步下调(如 0.1);
    • 将非语音阈值下调,提升对弱人声的敏感度;
    • 可尝试调小静音分割持续毫秒(如 300-400),避免长静音吞掉语音。
  3. 回到主界面点击设置更多参数,选中降噪,或选中分离人声背景声后重试(分离后的人声更纯净,VAD 更易切出)。
  4. 仍失败时,改用 openai-whisper(内置) 渠道 + large-v3 模型重试,或先用左侧 语音转录 功能单独测试该视频,判断是文件问题还是参数问题。
  5. 重试前务必勾选 清理已生成,避免复用上一次的空识别结果。

若以上均无效,请提供 logs/ 目录下最新日志文件底部约 30 行内容,以便进一步分析。

请查阅相关文档:

Thinking...
Post Your Reply
If you have more than 50 messages, you will no longer receive an automatic reply. Please ask a new question!
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Dondate via ko-fi.com

Related resource